[Corpora-List] State of Art of English or any Indian language WSD systems

[Siva Reddy]

Hi all,

Can anyone point me to the state of art of "English or Hindi (or any indian
language) supervised (minimally)  and unsupervised Word Sense
Disambiguation" systems. (All words WSD).

The system can only use the following resources.

1. Training and Testing Data consists of plain text. POS tag information is
also available.
2. For supervised systems, training data with annotated sense tags is
available.
3. Wordnet of the language.

We want to compare our system with the state of art systems and see where we
stand. The system need not be downloadable (I will be more happy if it is
downloadable). We need literature on the systems.

For English, if the systems are evaluated on semeval or senseval corpus,
they will be of more help to us. I could find Rada Mihalcea and Andras
Csomai (2005)*, *Rada Mihalcea and Ehsanul Faruque(2004).

Thanks,
Siva Reddy,
LTRC,
IIIT Hyderabad
http://iiit.ac.in
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20090211/94957830/attachment.htm>
-------------- next part --------------
_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora